Method and device for analyzing product market characteristics and electronic equipment

Abstract

The invention relates to the technical field of product marketing, and discloses a method and device for analyzing product market characteristics and electronic equipment, and the method comprises the steps: determining an analysis task of a target product, the analysis task comprising a screening target and an analysis target; according to the screening target, screening to obtain target social media data of the target product on the social media platform; based on a large language model, performing keyword analysis on the target social media data according to the analysis target to obtain keyword information; and performing analysis according to the keyword information to obtain market characteristics of the target product. The analysis task can be customized according to different screening targets and analysis targets, so that the analysis result better meets specific business requirements. The big language model is used for carrying out deep text analysis on the social media data, manual intervention is reduced, deeper user intentions and emotional tendencies can be mined, richer market insight is provided, and the analysis efficiency and the analysis depth of product market features are improved.

Description

Technical Field

[0001] This application relates to the technical field of product marketing, for example, to a method and device for analyzing product market characteristics, and an electronic device. Background Art

[0002] Currently, understanding the competitive product information of an enterprise's products is crucial for product marketing. It cannot be ignored that with the rapid growth of users on social media platforms, the marketing activities of competitive products on social media data and the information that the social media data of competitive products can bring to enterprises are increasing. How to effectively extract the marketing activity data of competitive products, as well as the relevant user posting data, and conduct in-depth analysis is an urgent problem to be solved.

[0003] In the related art, a method for classifying social media content based on a pre-trained classification model is disclosed. Through the preset tags of the user portrait, the data manually labeled is used to fine-tune and train the user needs, so as to realize the analysis of consumer user characteristics and the analysis of competitive product market information.

[0004] In the process of implementing the embodiments of the present disclosure, it is found that there are at least the following problems in the related art:

[0005] In the process of tag classification, the model needs to be fine-tuned and trained to improve the classification effect, and for each update of the user portrait tags, new training is required, making it difficult to quickly and deeply mine the potential information related to competitive products in social media content.

[0006] It should be noted that the information disclosed in the above background art section is only used to enhance the understanding of the background of this application, and therefore may include information that does not constitute the prior art known to those of ordinary skill in the art. Summary of the Invention

[0007] To have a basic understanding of some aspects of the disclosed embodiments, a simple summary is given below. The summary is not a general review, nor is it intended to identify key / important constituent elements or delineate the protection scope of these embodiments, but rather serves as a preamble to the subsequent detailed description.

[0008] The embodiments of the present disclosure provide a method and device for analyzing product market characteristics, and an electronic device, so as to improve the analysis efficiency and depth of product market characteristics.

[0009] In some embodiments, the method for analyzing the product market characteristics includes: determining the analysis tasks of the target product, where the analysis tasks include screening objectives and analysis objectives; screening and obtaining the target social media data of the target product on the social media platform according to the screening objectives; based on the large language model, performing keyword analysis on the target social media data according to the analysis objectives to obtain keyword information; and analyzing according to the keyword information to obtain the market characteristics of the target product.

[0010] Optionally, the screening objectives include the acquisition time period of the social media data, the target activity time period of the target product, and the screening metrics of the social media data; screening and obtaining the target social media data of the target product on the social media platform according to the screening objectives includes: within the acquisition time period, collecting the release data of the target product on the social media platform and determining the topic tags of each release data; determining the target topic tags according to the activity time period of each topic tag and the target activity time period; and determining the target social media data from the release data corresponding to the target topic tags according to the screening metrics.

[0011] Optionally, based on the large language model, performing keyword analysis on the target social media data according to the analysis objectives to obtain keyword information includes: based on the large language model, extracting keywords from the target social media data according to the analysis objectives to generate keywords; based on the large language model, classifying the keywords to generate keyword tags; and using the keyword tags as the keyword information.

[0012] Optionally, the analysis objectives include one or more analysis dimensions; the large language model extracts keywords from the target social media data in the following manner: analyzing the content of the target social media data and clarifying the specific meanings of each analysis dimension; and generating keywords under each analysis dimension according to the content of the target social media data and the specific meanings of the analysis dimensions.

[0013] Optionally, the large language model classifies the extracted keywords in the following manner: determining the tags with meanings similar to each keyword in the preset list of category tags; in the case where there are tags with meanings similar to the keyword, classifying the keyword into that tag; in the case where there are no tags with meanings similar to the keyword, using the keyword as a new tag; and after all the keywords are classified, outputting the classified list of category tags as the keyword tags.

[0014] Optionally, the large language model classifies the extracted keywords in the following manner: based on the clustering algorithm, performing keyword clustering on the extracted keywords to merge the keywords with inconsistent texts but similar content meanings; and adjusting the merged keywords to obtain the keyword tags.

[0015] Optionally, performing analysis based on the keyword information to obtain the market characteristics of the target product includes: performing statistical analysis on the keyword information to obtain statistical data; and generating the market characteristics of the target product based on the statistical data and basic information of the target product.

[0016] Optionally, market characteristics of the target product are generated based on statistical data and basic information of the target product, including: generating a data analysis report based on statistical data and basic information of the target product; analyzing the release status and development trend of the target product based on periodically generated data analysis reports, and generating reminder texts; and displaying the reminder texts and statistical data as market characteristics of the target product.

[0017] In some embodiments, the apparatus for analyzing product market characteristics includes a processor and a memory storing program instructions, and the processor is configured to execute the above-mentioned method for analyzing product market characteristics when running the program instructions.

[0018] In some embodiments, the electronic device includes: an electronic device body; and the device for analyzing product market characteristics as described above, which is installed in the electronic device body.

[0019] The method, device, and electronic device for analyzing product market characteristics provided by the embodiments of the present disclosure can achieve the following technical effects:

[0020] In the disclosed embodiment, the analysis task can be customized according to different screening objectives and analysis objectives, so that the analysis results are more in line with specific business needs. After determining the analysis task of the target product, the target social media data can be automatically screened, and the social media data can be analyzed based on the large language model, which reduces manual intervention and improves the efficiency of the analysis of product market characteristics. Using a large language model to perform deep text analysis on social media data can tap into deeper user intentions and emotional tendencies, provide richer market insights, and improve the depth of analysis of product market characteristics. In addition, the large language model can understand complex language structures and contexts, improve the accuracy of keyword extraction and market feature analysis, and can help decision makers make more informed business decisions by providing more accurate and in-depth market feature analysis.

[0021] The above general description and the following description are exemplary and explanatory only and are not intended to limit the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] One or more embodiments are exemplarily described by corresponding drawings, which do not limit the embodiments. Elements with the same reference numerals in the drawings are shown as similar elements, and the drawings do not constitute a scale limitation, and wherein:

[0023] Figure 1 It is a schematic diagram of a method for analyzing the market characteristics of products provided by an embodiment of the present disclosure;

[0024] Figure 2 It is a schematic diagram of another method for analyzing the market characteristics of products provided by an embodiment of the present disclosure;

[0025] Figure 3 It is a schematic diagram of another method for analyzing the market characteristics of products provided by an embodiment of the present disclosure;

[0026] Figure 4 It is a schematic diagram of a method for keyword analysis of target social media data based on a large language model provided by an embodiment of the present disclosure;

[0027] Figure 5 It is a schematic diagram of another method for analyzing the market characteristics of products provided by an embodiment of the present disclosure;

[0028] Figure 6 It is a schematic diagram of a device for analyzing the market characteristics of products provided by an embodiment of the present disclosure. Detailed implementation manners

[0029] In order to more comprehensively understand the features and technical content of the embodiments of the present disclosure, the implementation of the embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings. The accompanying drawings are only for reference and illustration purposes and are not used to limit the embodiments of the present disclosure. In the following technical descriptions, for the sake of explanation, sufficient understanding of the disclosed embodiments is provided through multiple details. However, one or more embodiments can still be implemented without these details. In other cases, well-known structures and devices can be shown in a simplified manner.

[0030] In the technical solutions described in this application, terms such as "first" and "second" are used to distinguish similar objects and do not necessarily describe a specific order or sequence. It should be understood that the data used in this way can be interchanged under appropriate circumstances so as to implement the embodiments of the present disclosure described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusion.

[0031] Unless otherwise specified, the term "plural" means two or more.

[0032] In the embodiments of the present disclosure, the character " / " indicates that the objects before and after are in an "or" relationship. For example, A / B means: A or B.

[0033] The term "and / or" is an associative relationship describing objects and indicates that three relationships can exist. For example, A and / or B means: A or B, or, A and B these three relationships.

[0034] The term "corresponding" may refer to an association relationship or a binding relationship. That A corresponds to B means there is an association relationship or a binding relationship between A and B.

[0035] Combine Figure 1 As shown, an embodiment of the present disclosure provides a method for analyzing the market characteristics of a product. The execution subject of this method may be a processor, and the method includes:

[0036] S101, the processor determines the analysis task of the target product, and the analysis task includes a screening target and an analysis target.

[0037] S102, the processor screens and obtains the target social media data of the target product on the social media platform according to the screening target.

[0038] S103, the processor performs keyword analysis on the target social media data based on the large language model according to the analysis target to obtain keyword information.

[0039] S104, the processor analyzes according to the keyword information to obtain the market characteristics of the target product.

[0040] In the embodiment of the present disclosure, the analysis task can be customized according to different screening targets and analysis targets, making the analysis result more in line with specific business requirements. After determining the analysis task of the target product, it is possible to automatically screen the target social media data and analyze the social media data based on the large language model, reducing manual intervention and improving the analysis efficiency of the product market characteristics. Using the large language model to perform in-depth text analysis on social media data can dig deeper into user intentions and sentiment tendencies, provide richer market insights, and improve the analysis depth of the product market characteristics. In addition, the large language model can understand complex language structures and contexts, improve the accuracy of keyword extraction and market characteristic analysis, and by providing more accurate and in-depth market characteristic analysis, it can help decision-makers make more informed business decisions.

[0041] Optionally, the screening target includes the acquisition time period of the social media data, the target activity time period of the target product, and the screening metrics of the social media data.

[0042] In this embodiment, the screening target determines which social media data will be used to analyze the market characteristics of the target product. The acquisition time period of social media data is the specific time period for collecting social media data, such as the most recent week, month, or during a specific marketing campaign. This can ensure that the data used for analysis is relevant to the current market situation, improving the timeliness and relevance of the analysis. The target activity time period of the target product is the specific time range for determining the activities or marketing events of the target product on social media, including long-term activities and short-term activities. By focusing on the data during a specific activity period, user feedback and market dynamics related to the activity can be captured more accurately. The screening metrics for social media data are the criteria used to screen social media data, such as the interaction volume of posts (publication, likes, comments, shares), mention volume, sentiment tendency, and influence metrics, etc. Taking the publication of posts as an example, only when there are more than 100 posts or more than 10% in the posts across the entire network can they be used as target social media data. By setting screening metrics, noise data can be eliminated and the most valuable information for analyzing the market characteristics of the target product can be extracted. Therefore, by setting screening targets, the data quality and analysis accuracy can be improved, and at the same time, the pertinence of the analysis can be enhanced.

[0043] Optionally, according to the screening target, the target social media data of the target product on the social media platform is screened and obtained, including: within the acquisition time period, collecting the publication data of the target product on the social media platform and determining the topic tags of each publication data; according to the activity time period of each topic tag and the target activity time period, determining the target topic tags; according to the screening metrics, determining the target social media data in the publication data corresponding to the target topic tags.

[0044] Combined Figure 2 As shown, another method for analyzing the market characteristics of a product provided by an embodiment of the present disclosure includes:

[0045] S201, the processor determines the analysis task of the target product, and the analysis task includes a screening target and an analysis target. The screening target includes the acquisition time period of social media data, the target activity time period of the target product, and the screening metrics for social media data.

[0046] S202, the processor collects the publication data of the target product on the social media platform within the acquisition time period and determines the topic tags of each publication data.

[0047] S203, the processor determines the target topic tags according to the activity time period of each topic tag and the target activity time period.

[0048] S204, the processor determines the target social media data in the publication data corresponding to the target topic tags according to the screening metrics.

[0049] S205: The processor performs keyword analysis on the target social media data based on the large language model and according to the analysis target to obtain keyword information.

[0050] S206: The processor performs analysis based on the keyword information to obtain market characteristics of the target product.

[0051] In this embodiment, by limiting the acquisition time period, it is possible to ensure that the collected data is closely related to the current market conditions and improve the timeliness of the analysis. The topic tags contained in each published data are extracted. These tags are usually used to identify the theme or activity of the post content. By matching the activity time period of the topic tag with the target activity time period, user feedback and market dynamics during a specific activity can be accurately captured. Finally, the screening indicators are applied to eliminate irrelevant data, improve data quality, and make the analysis results more in-depth and accurate.

[0052] Optionally, the target products include competing products of the enterprise's products.

[0053] In this embodiment, the competitor of the enterprise product is used as the target product, and the performance of the competitor on social media and user feedback can provide the enterprise with real-time competitive intelligence. By analyzing the market characteristics of the competitor, the enterprise can predict market trends and consumer behavior, so as to adjust its own market strategy in advance and better formulate differentiated products and market strategies to highlight its own advantages. Through competitive product analysis, the enterprise can also discover the shortcomings of its own products, thereby promoting product improvement and innovation.

[0054] Optionally, the target social media data of the competitor includes information on marketing activities of the competitor's enterprise on different social media platforms and information on social media content forwarding and comments of different users on the competitor's product.

[0055] In this embodiment, by using the target social media data of competitors, it is possible to more accurately analyze the market information of competitors in the target time period and predict consumer consumption behavior, generate better user portraits for target users, and tap into potential target customers, which helps to achieve precise marketing of corporate products and personalized promotion for consumers.

[0056] Optionally, the release data of the target product on the social media platform includes: content posted by official accounts, content posted by business orders, and content posted by ordinary users and consumers.

[0057] Optionally, determining the topic tags of each published data includes: for the content of each published data, obtaining all active topic tags in the content by methods such as regularized matching or large model extraction.

[0058] In this embodiment, topic tags are used to identify the theme or activity of the post content. The formats of topic tags include: "#topic#", "#topic", or other unformatted activity topic tags.

[0059] Optionally, according to the activity time period of each topic tag and the target activity time period, determine the target topic tag, including: determining whether the activity time period of each topic tag is a long-term activity or a short-term activity; according to the target activity time period, determine the target topic tag.

[0060] In this embodiment, according to the time when each topic first appears in the social media, it can be judged whether it is a short-term marketing activity topic or a long-term operation activity topic. According to the long-term activity or short-term activity corresponding to the target activity time period, determine the target topic tag that needs to be analyzed.

[0061] Optionally, the screening metrics include: one or more screening metrics such as the total number of valid posts corresponding to the target topic tag, the number of fans of the posting account, the total volume of the activity tag across the platform, and whether the product represented by the activity tag is a competing product that needs to be detected.

[0062] Optionally, based on the large language model, perform keyword analysis on the target social media data according to the analysis target to obtain keyword information, including: based on the large language model, extract keywords from the target social media data according to the analysis target to generate keywords; based on the large language model, classify the keywords to generate keyword tags; use the keyword tags as keyword information.

[0063] Combined Figure 3 As shown, another method for analyzing the market characteristics of a product provided by an embodiment of the present disclosure includes:

[0064] S301, the processor determines the analysis task of the target product, and the analysis task includes a screening target and an analysis target.

[0065] S302, the processor filters and obtains the target social media data of the target product on the social media platform according to the screening target.

[0066] S303, the processor extracts keywords from the target social media data based on the large language model according to the analysis target to generate keywords.

[0067] S304, the processor classifies the keywords based on the large language model to generate keyword tags.

[0068] S305, the processor uses the keyword tags as keyword information.

[0069] S306, the processor analyzes according to the keyword information to obtain the market characteristics of the target product.

[0070] In this embodiment, a large language model is used to extract and classify keywords from target social media data, obtaining keyword information. When processing target social media data such as user posts and advertising and marketing information, the large language model can understand complex contexts and semantics, improving the depth and breadth of keyword extraction. Based on in-depth analysis by the large language model, more accurate keywords can be obtained during the extraction process and more relevant keyword tags can be obtained during the classification process.

[0071] Optionally, the analysis objectives include one or more analysis dimensions. The analysis dimensions include: the name of the target product, the category of the target product, the target population of the target product, the selling points of the target product, the user pain points solved by the target product, and the usage scenarios of the target product.

[0072] In this embodiment, by setting the prompt template of the large language model, the large language model can perform keyword extraction under the required analysis dimensions. By clarifying the specific meaning of each analysis dimension, the accuracy of keyword extraction can be improved. Among them, the name of the target product refers to the specific name of the target product, which is used to identify and distinguish specific products in the market. The category of the target product: refers to the commodity category or market segment to which the target product belongs, such as smartphones, sports shoes, health foods, etc. The target population of the target product refers to the consumer group mainly targeted by the target product, usually defined according to factors such as age, gender, income, and interests. The selling points of the target product refer to the unique advantages and characteristics that attract consumers, such as high performance, low price, innovative technology, etc. The user pain points solved by the target product refer to the consumer problems and needs solved or alleviated by the target product, that is, the specific user needs met by the product. The usage scenarios of the target product refer to the specific occasions and environments in which the target product is used in real life, such as at home, in the office, during travel, etc.

[0073] Optionally, the large language model extracts keywords from the target social media data in the following manner: analyze the content of the target social media data and clarify the specific meaning of each analysis dimension; generate keywords under each analysis dimension according to the content of the target social media data and the specific meaning of the analysis dimension.

[0074] Combined with Figure 4 As shown, an embodiment of the present disclosure provides a large language model, and the large language model analyzes keywords in the target social media data according to the following method:

[0075] S401, the large language model analyzes the content of the target social media data and clarifies the specific meaning of each analysis dimension.

[0076] S402. The large language model generates keywords for each analysis dimension based on the content of the target social media data and the specific meaning of the analysis dimension, and executes S403 or S407.

[0077] S403. The large language model determines the labels with meanings similar to each keyword in the preset list of category labels, and executes S404 or S405.

[0078] S404. When there are labels with meanings similar to the keyword, the large language model classifies the keyword into that label and executes S406.

[0079] S405. When there are no labels with meanings similar to the keyword, the large language model takes the keyword as a new label and executes S406.

[0080] S406. After all keywords are classified, the large language model outputs the classified list of category labels as keyword labels and executes S409.

[0081] S407. The large language model performs keyword clustering on the extracted keywords based on a clustering algorithm, and merges keywords with inconsistent texts but similar content meanings.

[0082] S408. The large language model adjusts the merged keywords to obtain keyword labels and executes S409.

[0083] S409. The large language model outputs the keyword labels as keyword information.

[0084] In this embodiment, after setting the analysis dimension in the prompt template of the large language model, the large language model will analyze the content of the target social media data according to the corresponding prompt. After clarifying the specific meaning of each analysis dimension, it will quickly extract keywords for each analysis dimension through multi-threaded concurrency. For example, when the target product is a certain brand of refrigerator, the keywords for the target population of the target product may be "frugal people", "users concerned about energy conservation", etc.; the keywords for the selling points of the target product may be "low energy consumption", "automatic sterilization", etc.; the keywords for the user pain points solved by the target product may be: "poor refrigeration effect", "insufficient refrigerator space", etc.; the keywords for the usage scenarios of the target product may be "zero-embedded installation", "new house decoration", etc. Finally, the large language model returns the determined keywords in the defined data format, such as a json dictionary, list, etc., for subsequent parsing.

[0085] Optionally, the large language model classifies the extracted keywords as follows: in a preset list of category labels, determine the label that is similar in meaning to each keyword; in the case where there is a label similar in meaning to the keyword, classify the keyword under that label; in the case where there is no label similar in meaning to the keyword, use the keyword as a new label; after all keywords are classified, output the classified list of category labels as the keyword labels.

[0086] In this embodiment, the keywords determined by the large language model are complex and diverse, and may include multiple keywords with similar meanings. In order to simplify the obtained keywords, it is also necessary to classify the keywords to reduce the keywords with similar meanings. Through the preset list of category labels, different labels correspond to keywords with different meanings. Compare the keywords determined by the large language model with the category labels, and thus classify the keywords according to the category labels. In the case where there is no label similar in meaning to the keyword, use the keyword as a new label to ensure that all keywords are classified. For example, among the keywords of the selling points of a certain brand of refrigerator in the target product, there may be keywords with the same semantics but different expressions such as "energy saving", "low energy consumption", and "low power consumption". Since there is a label of "energy saving" in the category label list, these keywords can be classified under the "energy saving" label. After classification is completed, the large language model outputs the classified list of category labels. In this category label list, there are multiple category labels and the keywords under each category label.

[0087] Optionally, the large language model classifies the extracted keywords as follows: based on a clustering algorithm, perform keyword clustering on the extracted keywords to merge keywords with inconsistent texts but similar content meanings; adjust the merged keywords to obtain keyword labels.

[0088] In this embodiment, the large language model can also perform keyword clustering through a clustering algorithm, such as the K-means clustering algorithm, the DBSCAN clustering algorithm, etc., to achieve the classification of keywords. Keyword clustering can effectively compress the information density, merge feature words with inconsistent texts but the same content meanings, and optimize the information complexity of the results. After clustering is completed, the merged keywords can also be adjusted by adding manual review to make them more effectively summarize all the keywords under this clustering category.

[0089] Optionally, analyze the keyword information to obtain the market characteristics of the target product, including: performing statistical analysis on the keyword information to obtain statistical data; generating the market characteristics of the target product based on the statistical data and the basic information of the target product.

[0090] Combined with Figure 5As shown in the figure, an embodiment of the present disclosure provides another method for analyzing the market characteristics of a product, including:

[0091] S501, the processor determines the analysis task of the target product, and the analysis task includes a screening target and an analysis target.

[0092] S502, the processor screens and obtains the target social media data of the target product on the social media platform according to the screening target.

[0093] S503, the processor performs keyword analysis on the target social media data based on the large language model according to the analysis target to obtain keyword information.

[0094] S504, the processor performs statistical analysis on the keyword information to obtain statistical data.

[0095] S505, the processor generates the market characteristics of the target product according to the statistical data and the basic information of the target product.

[0096] In this embodiment, the keyword information is the analysis result obtained after multi-dimensional analysis of the target product. Through statistical analysis means such as screening and data pivoting of the keyword information, statistical data can be obtained. Through the set code, statistical charts can also be automatically generated according to the statistical data. Combining the statistical data and the basic information of the target product, the market characteristics of the target product can be determined.

[0097] Optionally, generating the market characteristics of the target product according to the statistical data and the basic information of the target product includes: generating a data analysis report according to the statistical data and the basic information of the target product; analyzing the release situation and development trend of the target product according to the periodically generated data analysis report to generate a reminder text; and displaying the reminder text and the statistical data as the market characteristics of the target product.

[0098] Optionally, the basic information of the target product includes: the basic information of the target product, historical data, and development trend.

[0099] In this embodiment, by using the large language model and the image multi-modal model, a corresponding data analysis report can be generated according to the statistical data and the basic information of the target product. After accumulating data analysis reports over multiple cycles, a situation reminder text can be generated for the development and launch situation of the target product to summarize the release situation and development trend of the target product within the cycle. Finally, in the display stage of the analysis result, the situation reminder text can be displayed in the form of a PPT or a document as the content of the analysis report of the target product, and the statistical chart and statistical data are provided to the dashboard system as data sources.

[0100] The method for analyzing product market characteristics provided by the embodiments of the present disclosure introduces generative language and image multi-modal large models, improves the automated extraction and analysis of data, and enables the analysis process to have higher reusability. By modifying the prompt words of the large language model, the analysis requirements can be customized. The framework has high reusability, significantly saving development time and model training time, and can ensure that the diversity and accuracy of the results are similar to those of manual analysis. In addition, for the analysis effect, it solves the problems in the current methods for analyzing social media content, such as single analysis dimension, inability to deeply interpret, and unreasonable divergence of results. In the data display stage, it saves the time for manually drawing tables and writing data analysis, greatly saving the labor time cost and improving the efficiency of generating social media data analysis reports.

[0101] As shown in combination Figure 6 The embodiments of the present disclosure provide an apparatus 600 for analyzing product market characteristics, including a processor 700 and a memory 701. Optionally, the apparatus may further include a communication interface 702 and a bus 703. Among them, the processor 700, the communication interface 702, and the memory 701 can communicate with each other through the bus 703. The communication interface 702 can be used for information transmission. The processor 700 can call the logical instructions in the memory 701 to execute the method for analyzing product market characteristics in the above embodiments.

[0102] In addition, when the logical instructions in the above memory 701 are implemented in the form of software functional units and sold or used as an independent product, they can be stored in a computer-readable storage medium.

[0103] The memory 701, as a computer-readable storage medium, can be used to store software programs and computer-executable programs, such as the program instructions / modules corresponding to the methods in the embodiments of the present disclosure. The processor 700 executes functional applications and data processing by running the program instructions / modules stored in the memory 701, that is, implements the method for analyzing product market characteristics in the above embodiments.

[0104] The memory 701 may include a program storage area and a data storage area. Among them, the program storage area may store an operating system and application programs required for at least one function; the data storage area may store data created according to the use of the terminal device, etc. In addition, the memory 701 may include high-speed random access memory and may also include non-volatile memory.

[0105] An embodiment of the present disclosure provides an electronic device, including: an electronic device body, and the above-described device for analyzing product market characteristics. The device for analyzing product market characteristics is installed on the electronic device body. The installation relationship described herein is not limited to being placed inside the electronic device, but also includes installation connections with other components of the electronic device, including but not limited to physical connections, electrical connections, or signal transmission connections, etc. Those skilled in the art can understand that the device for analyzing product market characteristics can be adapted to a feasible electronic device body, thereby implementing other feasible embodiments.

[0106] An embodiment of the present disclosure provides a computer-readable storage medium storing computer-executable instructions, and the computer-executable instructions are configured to execute the above-described method for analyzing product market characteristics.

[0107] The technical solution of an embodiment of the present disclosure can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in the embodiment of the present disclosure. The foregoing storage medium may be a non-transitory storage medium, including: a USB flash drive, a mobile hard disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk, or an optical disc, etc., which are various media that can store program codes.

[0108] The above description and the accompanying drawings fully illustrate the embodiments of the present disclosure, enabling those skilled in the art to practice them. Other embodiments may include structural, logical, electrical, process, and other changes. The embodiments merely represent possible variations. Unless explicitly required, individual components and functions are optional, and the order of operations may vary. Parts and features of some embodiments may be included in or replace parts and features of other embodiments. Moreover, the terms used in this application are only for describing the embodiments and do not limit the technical solutions described in this application. As used in the technical solutions described in this application, unless the context clearly indicates otherwise, the singular forms "a", "an", and "the" are intended to also include the plural forms. Similarly, as used in this application, the term "and / or" refers to any and all possible combinations including one or more of the associated listed items. Additionally, when used in this application, the term "comprise" and its variants "comprises" and / or "comprising" etc. mean the presence of the stated features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or groupings of these. Without further limitation, an element defined by the statement "comprising one..." does not exclude the presence of additional identical elements in the process, method, or device comprising the element. In this article, what each embodiment focuses on can be the differences from other embodiments, and the same or similar parts among the various embodiments can be referred to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method parts disclosed in the embodiments, the relevant parts can refer to the description of the method parts.

[0109] Those skilled in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner can depend on the specific application and design constraints of the technical solution. The skilled person can use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the embodiments of the present disclosure. The skilled person can clearly understand that for the convenience and brevity of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be elaborated herein.

[0110] In the embodiments disclosed herein, the disclosed methods, products (including but not limited to devices, equipment, etc.) can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units can be merely a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Additionally, the shown or discussed couplings or direct couplings or communication connections to each other can be through some interfaces. The indirect couplings or communication connections of the devices or units can be in electrical, mechanical, or other forms. The units described as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to implement this embodiment. Additionally, in the embodiments of the present disclosure, the various functional units can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit.

[0111] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram can represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing the specified logical function. In some alternative implementations, the functions marked in the blocks can occur in a different order than that marked in the accompanying drawings. For example, two consecutive blocks can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, which can depend on the functions involved. In the descriptions corresponding to the flowcharts and block diagrams in the accompanying drawings, the operations or steps corresponding to different blocks can also occur in a different order than that disclosed in the description. Sometimes, there is no specific order between different operations or steps. For example, two consecutive operations or steps can actually be executed substantially in parallel, and they can sometimes be executed in the reverse order, which can depend on the functions involved. Each block in the block diagram and / or flowchart, as well as the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or actions, or can be implemented by a combination of dedicated hardware and computer instructions.

Claims

1. A method for analyzing product market characteristics, characterized in that: include: Determine the analytical tasks for the target product, which include screening targets and analytical targets; According to the screening target, screen and obtain the target social media data of the target product on the social media platform; Based on the large language model, keyword analysis is performed on the target social media data according to the analysis objectives to obtain keyword information; Analyze based on keyword information to obtain the market characteristics of the target product.

2. The method according to claim 1, characterized in that The screening objectives include the acquisition time period of social media data, the target activity time period of the target product, and the screening indicators of social media data; According to the screening objectives, the target social media data of the target product on the social media platform is obtained through screening, including: During the acquisition period, collect the target product's release data on social media platforms and determine the topic tags for each release data; Determine the target topic tags based on the activity time period of each topic tag and the target activity time period; According to the screening indicators, the target social media data is determined from the publishing data corresponding to the target topic tag.

3. The method according to claim 1, characterized in that Based on the large language model, keyword analysis is performed on the target social media data according to the analysis objectives to obtain keyword information, including: Based on the large language model, keywords are extracted from the target social media data according to the analysis objectives to generate keywords; Based on the large language model, keywords are classified and keyword tags are generated; Use keyword tags as keyword information.

4. The method according to claim 3, characterized in that The analysis target includes one or more analysis dimensions; the large language model extracts keywords from the target social media data in the following manner: Analyze the content of the target social media data and clarify the specific meaning of each analysis dimension; Generate keywords under each analysis dimension based on the content of the target social media data and the specific meaning of the analysis dimension.

5. The method according to claim 3, characterized in that: The large language model classifies the extracted keywords as follows: In the preset category tag list, determine the tag that is similar to the meaning of each keyword; If there is a tag with a similar meaning to the keyword, the keyword is classified into the tag; If there is no tag with similar meaning to the keyword, the keyword is used as a new tag; After all keywords are classified, the classified category label list is output as keyword labels.

6. The method according to claim 3, characterized in that The large language model classifies the extracted keywords as follows: Based on the clustering algorithm, the extracted keywords are clustered and keywords with inconsistent texts but similar content and meaning are merged; Adjust the merged keywords to obtain keyword labels.

7. The method according to any one of claims 1 to 6, characterized in that: Analyze the keyword information to obtain the market characteristics of the target product, including: Conduct statistical analysis on keyword information to obtain statistical data; Generate the market characteristics of the target product based on statistical data and basic information of the target product.

8. The method according to claim 7, characterized in that Based on the statistical data and basic information of the target product, the market characteristics of the target product are generated, including: Generate data analysis reports based on statistical data and basic information of target products; Analyze the release and development trends of target products based on periodically generated data analysis reports and generate reminder texts; Present reminder texts and statistics as market features for target products.

9. A device for analyzing product market characteristics, comprising a processor and a memory storing program instructions, characterized in that: The processor is configured to execute the method for analyzing product market characteristics according to any one of claims 1 to 8 when running the program instructions.

10. An electronic device, characterized in that: include: an electronic device body; and an apparatus for analyzing product market characteristics as claimed in claim 9, mounted on the electronic device body.

Images